Pub Date : 2016-08-01DOI: 10.1109/ICSESS.2016.7883054
S. Qian, G. Weng
An approach for medical image segmentation based on Fuzzy C-Means (FCM) and Level Set algorithm is proposed in this paper. FCM algorithm is suitable for solving the problems of fuzzy and uncertainty in gray level images. Level Set algorithm can effectively solve the change of the topology of the curve evolution, and realize multiple-objects extraction. In this paper, first the noise is eliminated from background by median filtering and morphological filtering. Then the initial contour of the target is obtained through FCM algorithm. Finally the targets are segmented through multiple iterations of Level Set. The method has been tested on many images. Experimental results show that the proposed approach using FCM and Level Set algorithm for image segmentation is feasible and has a great effect.
{"title":"Medical image segmentation based on FCM and Level Set algorithm","authors":"S. Qian, G. Weng","doi":"10.1109/ICSESS.2016.7883054","DOIUrl":"https://doi.org/10.1109/ICSESS.2016.7883054","url":null,"abstract":"An approach for medical image segmentation based on Fuzzy C-Means (FCM) and Level Set algorithm is proposed in this paper. FCM algorithm is suitable for solving the problems of fuzzy and uncertainty in gray level images. Level Set algorithm can effectively solve the change of the topology of the curve evolution, and realize multiple-objects extraction. In this paper, first the noise is eliminated from background by median filtering and morphological filtering. Then the initial contour of the target is obtained through FCM algorithm. Finally the targets are segmented through multiple iterations of Level Set. The method has been tested on many images. Experimental results show that the proposed approach using FCM and Level Set algorithm for image segmentation is feasible and has a great effect.","PeriodicalId":175933,"journal":{"name":"2016 7th IEEE International Conference on Software Engineering and Service Science (ICSESS)","volume":"11 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133365238","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2016-08-01DOI: 10.1109/ICSESS.2016.7883086
Youan Xiao, Yan Han, Feng Yang
In server clusters, there are occasions where all the servers are allowed to sign messages on behalf of the whole cluster and manager can identify the signer at the same time. In this paper, we propose a new scheme called Traceable Certificate-Based Group Signature (TCBGS) which brings better efficiency, privacy and traceability. The scheme is constructed on elliptic curve discrete logarithm problem which decreases calculation, increases efficiency and security. Only one step are needed in signing and verifying, which is simple and efficient. With CA-certificates, all users can create secret keys on their own, communicate through open channel and join in the cluster dynamically. Meanwhile, signers can be identified by manager through opening the signature. The security and performance analysis shows that our scheme is more efficient and satisfies security requirement.
{"title":"Efficient Traceable digital signature scheme for server cluster","authors":"Youan Xiao, Yan Han, Feng Yang","doi":"10.1109/ICSESS.2016.7883086","DOIUrl":"https://doi.org/10.1109/ICSESS.2016.7883086","url":null,"abstract":"In server clusters, there are occasions where all the servers are allowed to sign messages on behalf of the whole cluster and manager can identify the signer at the same time. In this paper, we propose a new scheme called Traceable Certificate-Based Group Signature (TCBGS) which brings better efficiency, privacy and traceability. The scheme is constructed on elliptic curve discrete logarithm problem which decreases calculation, increases efficiency and security. Only one step are needed in signing and verifying, which is simple and efficient. With CA-certificates, all users can create secret keys on their own, communicate through open channel and join in the cluster dynamically. Meanwhile, signers can be identified by manager through opening the signature. The security and performance analysis shows that our scheme is more efficient and satisfies security requirement.","PeriodicalId":175933,"journal":{"name":"2016 7th IEEE International Conference on Software Engineering and Service Science (ICSESS)","volume":"67 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116159516","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2016-08-01DOI: 10.1109/icsess.2016.7883046
Ruhui Shen, Jialiang Shen, Yuhong Li, Haohan Wang
{"title":"Predicting usefulness of Yelp reviews with localized linear regression models","authors":"Ruhui Shen, Jialiang Shen, Yuhong Li, Haohan Wang","doi":"10.1109/icsess.2016.7883046","DOIUrl":"https://doi.org/10.1109/icsess.2016.7883046","url":null,"abstract":"","PeriodicalId":175933,"journal":{"name":"2016 7th IEEE International Conference on Software Engineering and Service Science (ICSESS)","volume":"57 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122082148","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2016-08-01DOI: 10.1109/ICSESS.2016.7883066
Zhifeng Luo, Chen Liang
Shilling attacks can affect the robustness and reliability of recommendation systems. There are many shilling attack detection schemes proposed in the literature. However, these schemes have not considered the case that the examiner who is in charge of shilling attack detections can be a malicious attacker. In this paper, we study the privacy issue in the shilling attack detection for recommendation systems. In our attack model, an examiner is assumed to be an attacker who is kept from the rating profiles by secure computations techniques. And we present a novel insider attack approach where the attacker only utilizes the output of secure computations and very little prior knowledge about ratings of a target user to infer the private rating profile. The experimental results illustrate that the proposed attack approach is very effective to breach privacy of users in the recommendation systems. It is proved that there is a serious risk to privacy in the shilling attack detection.
{"title":"An insider attack on shilling attack detection for recommendation systems","authors":"Zhifeng Luo, Chen Liang","doi":"10.1109/ICSESS.2016.7883066","DOIUrl":"https://doi.org/10.1109/ICSESS.2016.7883066","url":null,"abstract":"Shilling attacks can affect the robustness and reliability of recommendation systems. There are many shilling attack detection schemes proposed in the literature. However, these schemes have not considered the case that the examiner who is in charge of shilling attack detections can be a malicious attacker. In this paper, we study the privacy issue in the shilling attack detection for recommendation systems. In our attack model, an examiner is assumed to be an attacker who is kept from the rating profiles by secure computations techniques. And we present a novel insider attack approach where the attacker only utilizes the output of secure computations and very little prior knowledge about ratings of a target user to infer the private rating profile. The experimental results illustrate that the proposed attack approach is very effective to breach privacy of users in the recommendation systems. It is proved that there is a serious risk to privacy in the shilling attack detection.","PeriodicalId":175933,"journal":{"name":"2016 7th IEEE International Conference on Software Engineering and Service Science (ICSESS)","volume":"269 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122114701","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2016-08-01DOI: 10.1109/ICSESS.2016.7883090
Ma Li, Zhang Tao
To address the lack of health status identification and poor stability problems in the rotating machinery equipment, this paper proposes a new method for health status identification of rolling bearing based on SVM and improved evidence theory. Firstly, in order to reflect the rolling health condition, we use the empirical mode decomposition (EMD) to extract energy value and the original part of the signal statistics constitute characteristic parameters. After that we take them as the input to SVM classifier for the initial classification. Then we construct the basic probability assignment (BPA) by the SVM classification results. Finally, the results of recognition are given based on recursive dynamic combining weight distribution and decision fusion. The experimental results show that this method can effectively identify Rolling health status, which has high recognition accuracy, stability, and broad applicability.
{"title":"Health status identification of rolling bearing based on SVM and improved evidence theory","authors":"Ma Li, Zhang Tao","doi":"10.1109/ICSESS.2016.7883090","DOIUrl":"https://doi.org/10.1109/ICSESS.2016.7883090","url":null,"abstract":"To address the lack of health status identification and poor stability problems in the rotating machinery equipment, this paper proposes a new method for health status identification of rolling bearing based on SVM and improved evidence theory. Firstly, in order to reflect the rolling health condition, we use the empirical mode decomposition (EMD) to extract energy value and the original part of the signal statistics constitute characteristic parameters. After that we take them as the input to SVM classifier for the initial classification. Then we construct the basic probability assignment (BPA) by the SVM classification results. Finally, the results of recognition are given based on recursive dynamic combining weight distribution and decision fusion. The experimental results show that this method can effectively identify Rolling health status, which has high recognition accuracy, stability, and broad applicability.","PeriodicalId":175933,"journal":{"name":"2016 7th IEEE International Conference on Software Engineering and Service Science (ICSESS)","volume":"14 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122226577","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2016-08-01DOI: 10.1109/ICSESS.2016.7883158
Zhaojin Zhang, Cunlu Xu, W. Feng
The deep learning is a growing multi-layer neural network learning algorithm in the field of machine learning in recent years. Firstly, this paper analyzes the superiority of the deep learning at the aspect of feature extraction. Aimed at the lack of feature expression capacity and curse of dimensionality results from excessive feature dimensions of shallow learning, this paper proposes that using deep learning can extract high-lever features from low-lever features though its given layer structure. Secondly, the deep learning algorithm is applied in the case of road vehicle detection. Based on the traditional method, such as neural network the deep learning structure is further studied to increase the performance of feature extraction and classification recognition. Also, some tests are run in the Matlab software. The tests results show that with the increasing the amount of the data, the mean error and misclassification rate gradually decrease, so this algorithm based on the neural network has good superiority and adaptability of the deep learning. Finally, this paper proposes some suggestions for the improvement of the algorithm and prospects the development direction of the deep learning in the field of machine learning and artificial intelligence.
{"title":"Road vehicle detection and classification based on Deep Neural Network","authors":"Zhaojin Zhang, Cunlu Xu, W. Feng","doi":"10.1109/ICSESS.2016.7883158","DOIUrl":"https://doi.org/10.1109/ICSESS.2016.7883158","url":null,"abstract":"The deep learning is a growing multi-layer neural network learning algorithm in the field of machine learning in recent years. Firstly, this paper analyzes the superiority of the deep learning at the aspect of feature extraction. Aimed at the lack of feature expression capacity and curse of dimensionality results from excessive feature dimensions of shallow learning, this paper proposes that using deep learning can extract high-lever features from low-lever features though its given layer structure. Secondly, the deep learning algorithm is applied in the case of road vehicle detection. Based on the traditional method, such as neural network the deep learning structure is further studied to increase the performance of feature extraction and classification recognition. Also, some tests are run in the Matlab software. The tests results show that with the increasing the amount of the data, the mean error and misclassification rate gradually decrease, so this algorithm based on the neural network has good superiority and adaptability of the deep learning. Finally, this paper proposes some suggestions for the improvement of the algorithm and prospects the development direction of the deep learning in the field of machine learning and artificial intelligence.","PeriodicalId":175933,"journal":{"name":"2016 7th IEEE International Conference on Software Engineering and Service Science (ICSESS)","volume":"52 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124993062","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2016-08-01DOI: 10.1109/ICSESS.2016.7883221
Xiao Tan, Xiaoyu Wu, Cheng Yang
Chinese Traditional Visual Cultural Symbols(CT-VCSs) is the important component of Chinese ancient civilization, and it is the crystallization of Chinese culture with a history of several thousand years. So it has great significance to research CT-VCSs. In this paper, we mainly research the recognition and classification of CT-VCSs based on Convolutional neural network(CNN). We mainly use Caffenet and Alexnet in the Caffe framework, and fine-tune the existed Caffe models. Meanwhile, we also use GPU to speed up the process of training. Experimental results indicate that using CNN poses remarkable enhancement on the recognition task of CT-VCSs, and the recognition result of using Alexnet is the best.
{"title":"Chinese Traditional Visual Cultural Symbols recognition based on Convolutional neural network","authors":"Xiao Tan, Xiaoyu Wu, Cheng Yang","doi":"10.1109/ICSESS.2016.7883221","DOIUrl":"https://doi.org/10.1109/ICSESS.2016.7883221","url":null,"abstract":"Chinese Traditional Visual Cultural Symbols(CT-VCSs) is the important component of Chinese ancient civilization, and it is the crystallization of Chinese culture with a history of several thousand years. So it has great significance to research CT-VCSs. In this paper, we mainly research the recognition and classification of CT-VCSs based on Convolutional neural network(CNN). We mainly use Caffenet and Alexnet in the Caffe framework, and fine-tune the existed Caffe models. Meanwhile, we also use GPU to speed up the process of training. Experimental results indicate that using CNN poses remarkable enhancement on the recognition task of CT-VCSs, and the recognition result of using Alexnet is the best.","PeriodicalId":175933,"journal":{"name":"2016 7th IEEE International Conference on Software Engineering and Service Science (ICSESS)","volume":"6 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130179088","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2016-08-01DOI: 10.1109/ICSESS.2016.7883137
Anxuan Kuang, Shuyu Chen
Public or private cloud computing platform is often used to host multi-service platform. As a result of the adoption of virtual resource sharing architecture, multiple virtual machines corresponding to multi-service platform often contend for physical resources, including computing and storage as well as network resources, etc. This paper presents a method for resolving computing resource contention by using cloud platform virtual resource scheduling and resource thresholds, and provides service platform resource assurance. The experimental analysis of the solution here measures the feasibility of cloud resource scheduling solution. The program has been verified online.
{"title":"A study on cloud platform for multi-service virtual computing resource contention","authors":"Anxuan Kuang, Shuyu Chen","doi":"10.1109/ICSESS.2016.7883137","DOIUrl":"https://doi.org/10.1109/ICSESS.2016.7883137","url":null,"abstract":"Public or private cloud computing platform is often used to host multi-service platform. As a result of the adoption of virtual resource sharing architecture, multiple virtual machines corresponding to multi-service platform often contend for physical resources, including computing and storage as well as network resources, etc. This paper presents a method for resolving computing resource contention by using cloud platform virtual resource scheduling and resource thresholds, and provides service platform resource assurance. The experimental analysis of the solution here measures the feasibility of cloud resource scheduling solution. The program has been verified online.","PeriodicalId":175933,"journal":{"name":"2016 7th IEEE International Conference on Software Engineering and Service Science (ICSESS)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130354204","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2016-08-01DOI: 10.1109/ICSESS.2016.7883214
Aparajita Sahay, Min Chen
Plants are essential resources for nature and people's lives. Plant recognition provides valuable information for plant research and development, and has great impact on environmental protection and exploration. This paper presents a leaf analysis system for plant identification, which consists of three main components. First, given a leaf image, a preprocessing step is conducted for noise reduction. Second, the feature extraction component identifies representative features and computes scale invariant feature descriptors. Third, the matching plant species are identified and returned using a weighted K-nearest neighbor search algorithm. The system is implemented as a Windows phone app and is tested on the LeafSnapdataset[8], an electronic field guide developed by Columbia University and University of Maryland with different combinations of species at various orientations, scales and levels of brightness. The experimental results demonstrate the effectiveness of our proposed framework in plant recognition.
{"title":"Leaf analysis for plant recognition","authors":"Aparajita Sahay, Min Chen","doi":"10.1109/ICSESS.2016.7883214","DOIUrl":"https://doi.org/10.1109/ICSESS.2016.7883214","url":null,"abstract":"Plants are essential resources for nature and people's lives. Plant recognition provides valuable information for plant research and development, and has great impact on environmental protection and exploration. This paper presents a leaf analysis system for plant identification, which consists of three main components. First, given a leaf image, a preprocessing step is conducted for noise reduction. Second, the feature extraction component identifies representative features and computes scale invariant feature descriptors. Third, the matching plant species are identified and returned using a weighted K-nearest neighbor search algorithm. The system is implemented as a Windows phone app and is tested on the LeafSnapdataset[8], an electronic field guide developed by Columbia University and University of Maryland with different combinations of species at various orientations, scales and levels of brightness. The experimental results demonstrate the effectiveness of our proposed framework in plant recognition.","PeriodicalId":175933,"journal":{"name":"2016 7th IEEE International Conference on Software Engineering and Service Science (ICSESS)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128854379","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2016-08-01DOI: 10.1109/ICSESS.2016.7883040
Tingwei Gao, Xiu Li, Y. Chai, Youhua Tang
The stock market is an important component in the current economic market. And stock price prediction has recently garnered significant interest among investment brokers, individual investors and researchers. In general, stock market is very complex nonlinear dynamic system. Accordingly, accurate prediction of stock market is a very challenging task, owing to the inherent noisy environment and high volatility related to outside factors. In this paper, we focus on deep learning method to achieve high precision in stock market forecast. And a deep belief networks(DBNs), which is a kind of deep learning algorithm model, coupled with stock technical indicators(STIs) and two-dimensional principal component analysis((2D)2PCA) is introduced as a novel approach to predict the closing price of stock market. A comparison experiment is also performed to evaluate this model.
{"title":"Deep learning with stock indicators and two-dimensional principal component analysis for closing price prediction system","authors":"Tingwei Gao, Xiu Li, Y. Chai, Youhua Tang","doi":"10.1109/ICSESS.2016.7883040","DOIUrl":"https://doi.org/10.1109/ICSESS.2016.7883040","url":null,"abstract":"The stock market is an important component in the current economic market. And stock price prediction has recently garnered significant interest among investment brokers, individual investors and researchers. In general, stock market is very complex nonlinear dynamic system. Accordingly, accurate prediction of stock market is a very challenging task, owing to the inherent noisy environment and high volatility related to outside factors. In this paper, we focus on deep learning method to achieve high precision in stock market forecast. And a deep belief networks(DBNs), which is a kind of deep learning algorithm model, coupled with stock technical indicators(STIs) and two-dimensional principal component analysis((2D)2PCA) is introduced as a novel approach to predict the closing price of stock market. A comparison experiment is also performed to evaluate this model.","PeriodicalId":175933,"journal":{"name":"2016 7th IEEE International Conference on Software Engineering and Service Science (ICSESS)","volume":"34 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127705490","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：